Saiyam Pathak
Saiyam is working as Head of DevRel at vCluster Labs. He is the founder of Kubesimplify, focusing on simplifying cloud-native & AI infrastructure. He is KubeCon Co-chair and has worked on many facets of Kubernetes, including machine learning platforms, scaling, multi-cloud, & managed Kubernetes services. When not coding, Saiyam contributes to the community by writing blogs and organizing local meetups for Kubernetes and CNCF. He is also a CNCF TAG OpsRes Chair & can be reached on Twitter @saiyampathak.
How to Share GPUs in Kubernetes at Scale with HAMi (Software vGPU Slicing)
Share GPUs in Kubernetes with HAMi software vGPU slicing: arbitrary memory and core limits per pod, the Helm values that control the split, a verified PyTorch manifest, a real OOM blast-radius test, and Prometheus monitoring.
Slicing GPUs in Kubernetes with NVIDIA Multi-Instance GPU (MIG)
GPU sharing in Kubernetes explained: time-slicing vs MPS vs MIG, every nvidia-smi command to enable and disable MIG on one GPU or eight, GPU Operator automation, pitfalls, and DCGM monitoring.
Day 5: Local LLM Inference Engines, Wrappers, and What to Pick
A beginner-friendly guide to local LLM inference, with the same Qwen model tested through Ollama, llama.cpp, Docker Model Runner, vLLM, SGLang, and TensorRT-LLM on NVIDIA DGX Spark.
Bonsai 27B on RTX PRO 6000 vs DGX Spark: what actually works
Real Bonsai 27B benchmarks on an RTX PRO 6000 and a DGX Spark, including the supported llama.cpp setup, ternary vs 1-bit results, and speculative decoding.
Introducing kiac: Real Kubernetes Nodes on Your Mac, Each Its Own Lightweight VM
kiac runs local Kubernetes on macOS where every node is its own lightweight VM via apple/container: kubeadm or k3s flavors, Cilium on a custom kernel, built-in LoadBalancer, Grafana, Gateway API, and clusters that survive reboots.
Day 4: Quantization Demystified. BF16, FP8, NVFP4, MXFP4, INT4, GGUF, and Why It All Matters
A practical, beginner-friendly guide to BF16, FP8, NVFP4, MXFP4, INT4, and GGUF Q4_K_M on NVIDIA DGX Spark. Bytes per parameter, quality vs size, and which format to pick when.
Day 3: The DGX Spark Unpacked. GB10, Unified Memory, sm_121, and the One Reason This Hardware Exists
A practical teardown of NVIDIA DGX Spark's GB10 Grace Blackwell Superchip, unified memory, sm_121, NVFP4 tensor cores, memory reporting, and decode limits.
Wandler: Local OpenAI-Compatible Inference With Transformers.js and WebGPU
A practical Wandler deep dive with a local M1 Max WebGPU demo, real latency numbers, architecture diagrams, and getting-started commands.
mlxcel: A Rust-Native Inference Engine for Apple Silicon, Tested on My M1 Max
Day-one deep dive into mlxcel v0.1.0, a Rust-native MLX inference engine. Real M1 Max benchmarks vs mlx-lm and Ollama on Llama 3.2 3B and Qwen 2.5 7B, with architecture diagrams and an honest take on TurboQuant.
Day 2: Anatomy of an LLM Inference Request. From Prompt to Answer, Step by Step
A beginner-friendly walkthrough of tokenization, prefill, KV cache, decode, batching, TTFT, and why memory bandwidth shapes local LLM performance on NVIDIA DGX Spark.
How kube-proxy Actually Works: iptables, IPVS, and nftables Inside Out
How kube-proxy turns Kubernetes Services into kernel rules. iptables, IPVS, nftables packet paths and which to pick in 2026. Verified against k/k 1.36 source.
Day 1: The Local LLM Revolution. Why Your Desk Just Became the New Datacenter
Why local LLMs are becoming practical in 2026, what changed across open weights, hardware, and inference software, and why DGX Spark makes the desk feel like a small AI lab.
How Kubernetes EndpointSlices Actually Work (and Why Endpoints Had to Die)
A Service has no pod IPs in it. We covered that in the last post. So somewhere, something is keeping a list of every pod IP that matches the Service's…
NVCF Is Now Open Source: Inside NVIDIA's GPU Function Platform
NVIDIA just open-sourced the full NVCF platform under Apache 2.0. Not a thin SDK, not a client library. The actual control plane, invocation plane,…
How a Kubernetes Service Actually Works (and All 5 Types You Need)
A pod gets created. It gets an IP. Then it dies. A new pod replaces it. New IP. Now imagine you have ten pods of the same app, and they restart all the…
A Kubeconfig for GKE That Doesn't Need gcloud
When you run gcloud container clusters get-credentials , the kubeconfig it writes looks innocent — until you hand it to a teammate and they hit: …or the…
What Actually Happens When kube-scheduler Picks a Node (13 Stages Inside Kubernetes)
How kube-scheduler picks a node: 13 framework stages, 14 Filter plugins, 9 Score plugins, live preemption demo.
What Actually Happens When You Run kubectl run nginx
Every step of what happens when you run kubectl run nginx on Kubernetes. From argv to etcd Raft, scheduler, CRI, CNI, runc, and PLEG.
"SSH Into Your DGX Spark From Anywhere in the World Using Tailscale
Learn how to set up Tailscale on your NVIDIA DGX Spark for secure SSH access from anywhere in the world.
What Claude Code's Leaked Source Actually Teaches Us About Building AI Agents
512K lines of TypeScript, verified against actual source. The engineering patterns in Claude Code's leaked codebase that most coverage got wrong.
The Ingress NGINX Migration Just Got Easier: 119 Annotations, 3 Targets, Impact Ratings
"Ingress NGINX was archived March 24, 2026. ing-switch maps all 119 NGINX annotations with
clawspark: Your Private OpenClaw AI Assistant That Never Phones Home
Clawspark provides a way to Install openclaw on your device in a secure way with a single command.
Here's What I Learned About Nemotron 3 Super -I Ran a 120B Parameter Model on Nvidia DGX Spark
Understand everything about Nvidia DGX spark along with hands on and benchmarks.
ing-switch: Migrate from Ingress NGINX to Traefik or Gateway API in Minutes, Not Days
If you run Kubernetes, there's a deadline you can't ignore: Ingress NGINX is being deprecated in March 2026 . Roughly half of all Kubernetes clusters…
Kubernetes v1.33: Key Features, Updates, and What You Need to Know
"Kubernetes v1.33: Key Features, Updates, and What You Need to Know
Ephemeral Pull Request environment using Vcluster.
In a fast-paced development environment, having an isolated and ephemeral environment to test changes for every pull request (PR) is a game-changer. In…
Multi tenancy in 2025 and beyond
Multi-tenancy in Kubernetes has been an ongoing challenge for organizations looking to optimize their cloud-native infrastructure. Over the years, the appro
Confidential Containers - Running on Kubernetes
Confidential computing - it's not a fancy word anymore, it is something that has a whole ecosystem around it and also tooling to make it happen. Can we…
Announcing BuildSafe: Your Path to Secure Software Supply Chain
This post introduces BuildSafe that lets you build your application using nix with ease. It also helps you in securing your software supply chain.
My Journey to Kubestronaut on Kubernetes 10th Birthday
Journey to Kubestronaut, learning Kubernetes over the years and implementing at different organizations.
Why are network policies in Kubernetes so hard to understand?
This article explain in depth what network policies are with help of hands on examples to make the concepts clear.
The WebAssembly Course
In this course you will learn all the constructs of Webassembly required to get you ready for creating wasm based apps and run them on Kubernetes.
Kubesimplify - A Journey to remember
Kubesimplify is a community and a place to learn cloud-native in a simple way by working of projects and contributing your learning for others.
Demystifying API Response in Go
How to handle API response as text, HTML or JSON using GoLang.
Kubernetes backup using CloudCasa
Easy Kubernetes backup and restore using CloudCasa.
Cool Cool Coolify...
It's not a fancy title!! Coolify is actually a new fancy product that is an open-source & self-hostable Heroku / Netlify alternative! You can simply…
Rancher Desktop evolution
I have been testing out and using Rancher desktop since it originally came out, did a stream and a walkthrough video as well. When Rancher desktop…